arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.02774cs.CVcs.LG
收藏

绘制您自己的GAN

Sketch Your Own GAN

Carnegie Mellon University(卡内基梅隆大学);MIT CSAIL(麻省理工学院计算机科学与人工智能实验室)

Sheng-Yu Wang, David Bau, Jun-Yan Zhu

摘要:

用户可以通过绘制单个示例来创建深度生成模型吗?传统上,创建GAN模型需要收集大规模的样本数据集和深度学习的专业知识。相比之下,草图可能是传达视觉概念的最普遍的方式。在这项工作中,我们提出了一种方法,GAN草图,用于重写GANs与一个或多个草图,使GANs培训更容易为新手用户。特别地,我们根据用户草图改变原始GAN模型的权重。我们鼓励模型的输出通过跨域对抗损失来匹配用户草图。此外,我们探索不同的正则化方法,以保持原始模型的多样性和图像质量。实验表明,我们的方法可以塑造GANs,以匹配草图指定的形状和姿势,同时保持真实感和多样性。最后,我们展示了所得到的GAN的一些应用,包括潜在空间插值和图像编辑。

英文摘要:

Can a user create a deep generative model by sketching a single example? Traditionally, creating a GAN model has required the collection of a large-scale dataset of exemplars and specialized knowledge in deep learning. In contrast, sketching is possibly the most universally accessible way to convey a visual concept. In this work, we present a method, GAN Sketching, for rewriting GANs with one or more sketches, to make GANs training easier for novice users. In particular, we change the weights of an original GAN model according to user sketches. We encourage the model's output to match the user sketches through a cross-domain adversarial loss. Furthermore, we explore different regularization methods to preserve the original model's diversity and image quality. Experiments have shown that our method can mold GANs to match shapes and poses specified by sketches while maintaining realism and diversity. Finally, we demonstrate a few applications of the resulting GAN, including latent space interpolation and image editing.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑